© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21919
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or periods in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iva
    -0.70
    anka
    -0.70
     âĢķ
    -0.70
    ulner
    -0.66
    itiz
    -0.65
    tons
    -0.65
    itiveness
    -0.65
    arians
    -0.64
    deals
    -0.64
    bnb
    -0.62
    POSITIVE LOGITS
     midst
    1.27
     autumn
    1.21
     wee
    1.15
     aftermath
    1.11
     spring
    1.10
     waning
    1.06
     wake
    1.05
     summer
    1.04
     fall
    0.99
     guise
    0.97
    Activations Density 0.133%

    No Known Activations